Towards Learning Universal, Regional, and Local Hydrological Behaviors via Machine-Learning Applied to Large-Sample Datasets

TL;DR

This paper introduces a novel LSTM-based machine learning approach for regional rainfall-runoff modeling that outperforms traditional hydrological models, leveraging large datasets and an adapted architecture to learn catchment similarities.

Contribution

The paper presents a new data-driven LSTM approach for hydrological modeling that improves performance over existing models and introduces an Entity-Aware-LSTM architecture for capturing catchment similarities.

Findings

LSTM models outperform traditional hydrological models in regional rainfall-runoff prediction.

Training on large datasets enables a single model to generalize across multiple basins.

Entity-Aware-LSTM captures catchment similarities aligning with hydrological understanding.

Abstract

Regional rainfall-runoff modeling is an old but still mostly out-standing problem in Hydrological Sciences. The problem currently is that traditional hydrological models degrade significantly in performance when calibrated for multiple basins together instead of for a single basin alone. In this paper, we propose a novel, data-driven approach using Long Short-Term Memory networks (LSTMs), and demonstrate that under a 'big data' paradigm, this is not necessarily the case. By training a single LSTM model on 531 basins from the CAMELS data set using meteorological time series data and static catchment attributes, we were able to significantly improve performance compared to a set of several different hydrological benchmark models. Our proposed approach not only significantly outperforms hydrological models that were calibrated regionally but also achieves better performance than hydrological models that were calibrated for each basin individually. Furthermore, we propose an adaption to the standard LSTM architecture, which we call an Entity-Aware-LSTM (EA-LSTM), that allows for learning, and embedding as a feature layer in a deep learning model, catchment similarities. We show that this learned catchment similarity corresponds well with what we would expect from prior hydrological understanding.